Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.2730. Min Act: -0.0000

Data Index: 31835 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1557009 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.2320. Min Act: -0.0000

Data Index: 374483 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1197304 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1670928 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1630. Min Act: -0.0000

Data Index: 306570 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1283981 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1626. Min Act: -0.0000

Data Index: 559665 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1118. Min Act: -0.0000

Data Index: 1268700 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1808147 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.0641. Min Act: -0.0000

Data Index: 949994 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1181483 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1996129 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1462358 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1618226 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1416862 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1530300 (The Pile)

Max Activating Token Index: 60

Text #17

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.1366. Min Act: -0.0000

Data Index: 1077430 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.0386. Min Act: -0.0000

Data Index: 710835 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.3259. Min Range: -1.3259

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1774806 (The Pile)

Max Activating Token Index: 634